山东理工大学学报（自然科学版）2025，Vol.39Issue(5)：42-49,8.
基于改进OC-SORT和运动信息估计的团队体育多目标跟踪
Multi-object tracking in team sports based on improved OC-SORT and motion information estimation
摘要
Abstract
With the development of object detection and re-identification algorithms,multi-object tracking(MOT)has made rapid progress.However,tracking multiple athletes with similar appearances and nonlinear movements in team sports remains a pressing challenge.Current motion-based tracking al-gorithms typically employ the Kalman Filter to predict target motion,but they struggle to handle nonlinear movements and mutual occlusions among multiple targets effectively.To address this,we propose a MOT framework based on improved OC-SORT and motion information estimation,utilizing the Transformer ar-chitecture as a motion predictor instead of the Kalman Filter.We introduce historical trajectory embed-dings to extract spatiotemporal features from sequences of previously detected bounding boxes.During the association phase between current detections and historical trajectories,accurate matching is achieved u-sing the Hungarian algorithm based on Buffered Intersection Over Union(BIoU).Furthermore,we design different post-processing procedures for three team sports,basketball,soccer,and volleyball,to ef-fectively handle athletes'nonlinear movements on the field.Experimental results show that the proposed method achieves HOTA score of 77.3％and IDF1 of 78.2％on the SportsMOT public dataset,outperfor-ming other state-of-the-art methods.This demonstrates the effectiveness and robustness of the proposed framework in MOT tasks for various team sports,including basketball,soccer,and volleyball.关键词
多目标跟踪/团队体育/运动预测器/轨迹嵌入/非线性移动Key words
multi-object tracking/team sports/motion predictor/trajectory embedding/nonlinear mo-tion分类
信息技术与安全科学引用本文复制引用
戚琦,曹伟,王晓勇..基于改进OC-SORT和运动信息估计的团队体育多目标跟踪[J].山东理工大学学报（自然科学版）,2025,39(5):42-49,8.基金项目
安徽省教育厅高等学校省级质量工程项目(2021jxtd259) （2021jxtd259）
安徽省高等学校科学研究重点项目(2023AH051146) （2023AH051146）
